Meta AI Wins Gold in 5 STEM Olympiads with Pure LLM Reasoning
PMinervini · x · 2026-08-07
Meta officially announced that its latest AI models competed in five STEM Olympiad competitions, achieving perfect scores in physics theory exams and gold-medal-level performances in math and chemistry.
A community member highlighted that to test pure reasoning capability, Meta disallowed all tool use and coding. This means the model relied purely on autoregressive (AR) LLM mechanisms for deep logical inference, without relying on external symbolic computation tools.
More from Models
- GPT Auto-Titles Conversation in Chinese, Baffling User — rodrigoinfloripa · 2026-08-26
- QUASAR Releases Fully Quantized NVFP4 Qwen3.8-27B, Near-BF16 Performance — arty_photography · 2026-08-26
- Test: Qwen 3.8B with MTP boosts feasibility — adrianscottcom · 2026-08-26
- Benchmark: Kimi K3 outperforms Codex in kernel optimization task — Xianbao_QIAN · 2026-08-26
- Doubts cast on low ranking of Gemini 3.7 Flash — scaling01 · 2026-08-26
- Ex-OpenAI Staff Laments GPT-4.5's Unmatched User Experience — adonis_singh · 2026-08-26